<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rajan-etal-2024-knowledge">
    <titleInfo>
        <title>Knowledge-based Consistency Testing of Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sai</namePart>
        <namePart type="given">Sathiesh</namePart>
        <namePart type="family">Rajan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ezekiel</namePart>
        <namePart type="family">Soremekun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sudipta</namePart>
        <namePart type="family">Chattopadhyay</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this work, we systematically expose and measure the inconsistency and knowledge gaps of Large Language Models (LLMs). Specifically, we propose an automated testing framework (called KONTEST) which leverages a knowledge graph to construct test cases. KONTEST probes and measures the inconsistencies in the LLM‘s knowledge of the world via a combination of semantically-equivalent queries and test oracles (metamorphic or ontological oracle). KONTEST further mitigates knowledge gaps via a weighted LLM model ensemble. Using four state-of-the-art LLMs (Falcon, Gemini, GPT3.5, and Llama2), we show that KONTEST generates 19.2% error inducing inputs (1917 errors from 9979 test inputs). It also reveals a 16.5% knowledge gap across all tested LLMs. A mitigation method informed by KONTEST‘s test suite reduces LLM knowledge gap by 32.48%. Our ablation study further shows that GPT3.5 is not suitable for knowledge-based consistency testing because it is only 60%-68% effective in knowledge construction.</abstract>
    <identifier type="citekey">rajan-etal-2024-knowledge</identifier>
    <identifier type="doi">10.18653/v1/2024.findings-emnlp.596</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-emnlp.596/</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>10185</start>
            <end>10196</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Knowledge-based Consistency Testing of Large Language Models
%A Rajan, Sai Sathiesh
%A Soremekun, Ezekiel
%A Chattopadhyay, Sudipta
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F rajan-etal-2024-knowledge
%X In this work, we systematically expose and measure the inconsistency and knowledge gaps of Large Language Models (LLMs). Specifically, we propose an automated testing framework (called KONTEST) which leverages a knowledge graph to construct test cases. KONTEST probes and measures the inconsistencies in the LLM‘s knowledge of the world via a combination of semantically-equivalent queries and test oracles (metamorphic or ontological oracle). KONTEST further mitigates knowledge gaps via a weighted LLM model ensemble. Using four state-of-the-art LLMs (Falcon, Gemini, GPT3.5, and Llama2), we show that KONTEST generates 19.2% error inducing inputs (1917 errors from 9979 test inputs). It also reveals a 16.5% knowledge gap across all tested LLMs. A mitigation method informed by KONTEST‘s test suite reduces LLM knowledge gap by 32.48%. Our ablation study further shows that GPT3.5 is not suitable for knowledge-based consistency testing because it is only 60%-68% effective in knowledge construction.
%R 10.18653/v1/2024.findings-emnlp.596
%U https://aclanthology.org/2024.findings-emnlp.596/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.596
%P 10185-10196

Markdown (Informal)

[Knowledge-based Consistency Testing of Large Language Models](https://aclanthology.org/2024.findings-emnlp.596/) (Rajan et al., Findings 2024)

• Knowledge-based Consistency Testing of Large Language Models (Rajan et al., Findings 2024)

ACL

• Sai Sathiesh Rajan, Ezekiel Soremekun, and Sudipta Chattopadhyay. 2024. Knowledge-based Consistency Testing of Large Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10185–10196, Miami, Florida, USA. Association for Computational Linguistics.